Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
Li, Hao, Sun, Yizheng, Schlegel, Viktor, Yang, Kailai, Batista-Navarro, Riza, Nenadic, Goran
–arXiv.org Artificial Intelligence
Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering of argumentative components, the generation stage remains underexplored. Existing approaches typically rely on single-pass generation, offering limited support for factual correction or structural refinement. To address this gap, we introduce Arg-LLaDA, a novel large language diffusion framework that iteratively improves summaries via sufficiency-guided remasking and regeneration. Our method combines a flexible masking controller with a sufficiency-checking module to identify and revise unsupported, redundant, or incomplete spans, yielding more faithful, concise, and coherent outputs. Empirical results on two benchmark datasets demonstrate that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 automatic evaluation metrics. In addition, human evaluations reveal substantial improvements across core dimensions, coverage, faithfulness, and conciseness, validating the effectiveness of our iterative, sufficiency-aware generation strategy.
arXiv.org Artificial Intelligence
Nov-21-2025
- Country:
- Asia > Singapore (0.04)
- Europe > United Kingdom
- England > Greater Manchester > Manchester (0.04)
- Genre:
- Research Report (1.00)
- Industry:
- Health & Medicine > Therapeutic Area
- Immunology (0.68)
- Law (0.68)
- Health & Medicine > Therapeutic Area
- Technology: